CN117233605A - New energy automobile fault pre-judging method based on Internet of things - Google Patents
New energy automobile fault pre-judging method based on Internet of things Download PDFInfo
- Publication number
- CN117233605A CN117233605A CN202310995405.2A CN202310995405A CN117233605A CN 117233605 A CN117233605 A CN 117233605A CN 202310995405 A CN202310995405 A CN 202310995405A CN 117233605 A CN117233605 A CN 117233605A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- fault
- data set
- new energy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 230000005856 abnormality Effects 0.000 claims description 17
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000004092 self-diagnosis Methods 0.000 claims description 7
- 238000003745 diagnosis Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The invention belongs to the technical field of automobile fault diagnosis, and particularly relates to a new energy automobile fault pre-judging method based on the Internet of things, which comprises the following steps: step 1, acquiring vehicle operation data of a current new energy automobile; step 2, processing vehicle operation data, classifying according to data types, and comparing the data with a sample data set to judge whether abnormal data exist or not; if yes, generating a vehicle suspicious data set; step 3, preprocessing a vehicle suspicious data set, inputting the vehicle suspicious data set into a function model, outputting a judging result, and analyzing a fault reason according to the judging result to obtain vehicle fault data; and 4, taking corresponding emergency measures according to the vehicle fault data. The invention can effectively predict and diagnose the automobile faults in time and improve the use safety of the automobile.
Description
Technical Field
The invention belongs to the technical field of automobile fault diagnosis, and particularly relates to a new energy automobile fault pre-judging method based on the Internet of things.
Background
The new energy automobile can reduce pollution emission due to the use of clean energy, so that more and more people select the new energy automobile as a travel tool. The new energy automobile adopts motor drive, has the characteristics of wide speed regulation range, large starting torque, large backup power and high efficiency, and usually performs battery fault detection before the new energy automobile leaves the factory so as to ensure safe use of the battery. Meanwhile, a fault diagnosis system is usually arranged on the new energy automobile to detect faults when the new energy automobile runs, but the defects of incomplete diagnosis, untimely treatment and the like are still faced, the faults of the automobile cannot be timely and effectively predicted and diagnosed, and the use safety of the new energy automobile is reduced.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a new energy automobile fault pre-judging method based on the Internet of things, which can effectively pre-judge and diagnose automobile faults in time and improve the use safety of automobiles.
The technical scheme adopted for solving the technical problems is as follows:
a new energy automobile fault pre-judging method based on the Internet of things comprises the following steps:
step 1, acquiring vehicle operation data of a current new energy automobile;
step 2, processing vehicle operation data, classifying according to data types, and comparing the data with a sample data set to judge whether abnormal data exist or not; if yes, generating a vehicle suspicious data set;
step 3, preprocessing a vehicle suspicious data set, inputting the vehicle suspicious data set into a function model, outputting a judging result, and analyzing a fault reason according to the judging result to obtain vehicle fault data;
and 4, taking corresponding emergency measures according to the vehicle fault data.
Further, in step 2, a data processing process is performed on the vehicle, including:
step 21, classifying the vehicle operation data and encoding the classification; such as classifying data as: battery data, sensor data, and gearbox data;
step 22, normalizing the encoded vehicle operation data to obtain a normalized data set c= [ C ] 1 ,c 2 ...c n ]Wherein c n Vehicle operation data representing an nth category;
step 23, importing the data set into a corresponding database according to a preset format, and comparing the data set with the sample data set.
Further, in the step 3, the suspicious vehicle data set is preprocessed and input into the function model, specifically: for a vehicle operation data set c= [ C ] with n categories 1 ,c 2 ...c n ]Comparing the operation data with upper and lower limits in a feasible domain for the ith (i=1, 2..n.) classification, judging whether data abnormality exists, if so, calculating the abnormality probability of the data, dividing the data with the abnormality probability smaller than the abnormality threshold of the data into a normal data set, and dividing the data with the abnormality probability smaller than the abnormality threshold of the data into the operation numberAccording to the abnormal data set.
Further, the calculation formula of the data anomaly probability is as follows:
wherein d i (i＝1、2...n)、C 0 、D 0 Are all parameters, and C 0 ＞c i (i＝1、2...n)，D 0 ＞d i (i＝1、2...n)。
Further, dividing the data with the abnormal probability smaller than the abnormal threshold value of the data into a normal data set, marking the data, and calculating the association degree W of the occurrence probability of the data and the abnormal probability of the data:
wherein Q is n The occurrence probability corresponding to the n-th normal data set.
Furthermore, when the association degree W is smaller than a preset threshold value, no alarm is sent out, and if the association degree W is larger than the preset threshold value, an early warning is sent out to prompt that the probability of abnormality of the type of data is larger, and corresponding equipment needs to be checked in time to early warn, so that the occurrence of faults is reduced.
The invention also provides another technical scheme:
the utility model provides a new energy automobile trouble prejudgement system based on thing networking for realize the method, include:
the information acquisition module is used for acquiring vehicle operation data of the current new energy automobile;
the real-time monitoring module is used for receiving the vehicle running data, monitoring the vehicle running state in real time, and generating vehicle suspicious data if the running state is abnormal;
the fault self-diagnosis module is used for receiving the generated vehicle suspicious data, pre-judging whether the vehicle running state has a fault according to the generated vehicle suspicious data, if the vehicle running state does not have the fault, recording the occurrence times of the generated vehicle suspicious data, if the vehicle running state does not have the fault, generating vehicle fault data, and simultaneously sending out a warning;
and the fault processing module is used for receiving the vehicle fault data and taking emergency measures according to the vehicle fault data.
Further, the vehicle operation data at least comprises motor operation parameters of the new energy automobile: battery pack ID number, voltage, current, motor temperature, power, remaining power, number of charges, etc.
Further, the fault self-diagnosis module includes:
the data preprocessing module is used for preprocessing a suspicious data set of the vehicle;
the function model building module is used for building a function model, receiving the data transmitted by the data processing module and dividing a normal data set and an abnormal data set;
and the fault analysis module is used for analyzing and determining faults according to the abnormal data set.
Further, the vehicle operation data further comprises sensor parameters and gearbox parameters.
The invention has the technical effects that:
compared with the prior art, the new energy automobile fault pre-judging method based on the Internet of things is characterized in that firstly, vehicle operation data are processed, whether abnormal data exist or not is judged after the data are classified, then, a vehicle suspicious data set is preprocessed and input into a function model, so that fault reasons are analyzed, vehicle fault data are generated, corresponding emergency measures are conveniently taken, automobile faults are effectively pre-judged and diagnosed in time, and the use safety of an automobile is improved.
Drawings
Fig. 1 is a flow chart of a new energy automobile fault pre-judging method based on the internet of things.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the accompanying drawings of the specification.
Example 1:
the embodiment relates to a new energy automobile fault pre-judging method based on the Internet of things, which comprises the following steps:
step 1, acquiring vehicle operation data of a current new energy automobile;
step 2, processing vehicle operation data, classifying according to data types, and comparing the data with a sample data set to judge whether abnormal data exist or not; if yes, generating a vehicle suspicious data set; the method specifically comprises the following steps:
step 21, classifying the vehicle operation data and encoding the classification; such as classifying data as: battery data, sensor data, and gearbox data;
step 22, normalizing the encoded vehicle operation data to obtain a normalized data set c= [ C ] 1 ,c 2 ...c n ]Wherein c n Vehicle operation data representing an nth category;
step 23, importing the data set into a corresponding database according to a preset format, and comparing the data set with the sample data set;
step 3, preprocessing a vehicle suspicious data set, inputting the vehicle suspicious data set into a function model, outputting a judging result, and analyzing a fault reason according to the judging result to obtain vehicle fault data; specifically, for a vehicle operation data set c= [ C ] having n categories 1 ,c 2 ...c n ]Comparing the operation data of the class with the upper limit and the lower limit in the feasible domain for the ith (i=1, 2..n.) classification, judging whether data abnormality exists, and if so, calculating the abnormality probability p of the data of the class n ：
Wherein d i (i＝1、2...n)、C 0 、D 0 Are all parameters, and C 0 ＞c i (i＝1、2...n)，D 0 ＞d i (i=1, 2..n); the anomaly probability is smaller thanDividing the data of the data abnormal threshold into a normal data set, and dividing the data with the abnormal probability smaller than the data abnormal threshold into an abnormal data set of the operation data;
and 4, taking corresponding emergency measures according to the vehicle fault data.
In order to prevent faults in advance, the method divides data with the abnormal probability smaller than the abnormal threshold value of the data into normal data sets, marks the data, and calculates the association degree W of the occurrence probability of the data and the abnormal probability of the data:
wherein Q is n The occurrence probability corresponding to the n-th normal data set. When the association degree W is smaller than a preset threshold value, no alarm is sent out, and if the association degree W is larger than the preset threshold value, an early warning is sent out to prompt that the probability of abnormality of the type of data is larger, and corresponding equipment needs to be checked in time to early warn in order to reduce the occurrence of faults.
Example 2:
the embodiment relates to a new energy automobile fault pre-judging system based on the Internet of things, which is used for realizing the method described in the embodiment 1 and comprises an information acquisition module, a real-time monitoring module, a fault self-diagnosis module and a fault processing module; the information acquisition module is used for acquiring vehicle operation data of the current new energy automobile; the real-time monitoring module is used for receiving the vehicle running data, monitoring the vehicle running state in real time, and generating vehicle suspicious data if the running state is abnormal; the fault self-diagnosis module is used for receiving the generated vehicle suspicious data, pre-judging whether the vehicle running state has a fault or not according to the generated vehicle suspicious data, if the vehicle running state does not have the fault, recording the occurrence times of the generated vehicle suspicious data, if the vehicle running state does not have the fault, generating vehicle fault data, and simultaneously giving a warning; the fault processing module is used for receiving the vehicle fault data and taking emergency measures according to the vehicle fault data.
The vehicle operation data includes motor operation parameters (battery pack ID number, voltage, current, motor temperature, power, remaining power, number of times of charging), sensor parameters, gearbox parameters, and the like of the new energy automobile.
The fault self-diagnosis module comprises a data preprocessing module, a function model building module and a fault analysis module; the data preprocessing module is used for preprocessing a suspicious data set of the vehicle; the function model building module is used for building a function model, receiving the data transmitted by the data processing module and dividing a normal data set and an abnormal data set; the fault analysis module is used for analyzing and determining faults according to the abnormal data set.
The above embodiments are merely examples of the present invention, and the scope of the present invention is not limited to the above embodiments, and any suitable changes or modifications made by those skilled in the art, which are consistent with the claims of the present invention, shall fall within the scope of the present invention.
Claims (10)
1. The new energy automobile fault pre-judging method based on the Internet of things is characterized by comprising the following steps of:
step 1, acquiring vehicle operation data of a current new energy automobile;
step 2, processing vehicle operation data, classifying according to data types, and comparing the data with a sample data set to judge whether abnormal data exist or not; if yes, generating a vehicle suspicious data set;
step 3, preprocessing a vehicle suspicious data set, inputting the vehicle suspicious data set into a function model, outputting a judging result, and analyzing a fault reason according to the judging result to obtain vehicle fault data;
and 4, taking corresponding emergency measures according to the vehicle fault data.
2. The new energy automobile fault pre-judging method based on the internet of things according to claim 1, wherein in step 2, the vehicle operation data processing process comprises the following steps:
step 21, classifying the vehicle operation data and encoding the classification;
step 22, normalizing the encoded vehicle operation data to obtain a normalized data set c= [ C ] 1 ,c 2 ...c n ]Wherein c n Vehicle operation data representing an nth category;
step 23, importing the data set into a corresponding database according to a preset format, and comparing the data set with the sample data set.
3. The method for predicting the failure of the new energy automobile based on the internet of things according to claim 2, wherein in the step 3, the suspicious data set of the automobile is preprocessed and input into a function model, specifically:
for a vehicle operation data set c= [ C ] with n categories 1 ,c 2 ...c n ]Comparing the operation data with upper and lower limits in a feasible domain for the ith (i=1, 2..n.) classification, judging whether data abnormality exists, if so, calculating the abnormality probability of the data, dividing the data with the abnormality probability smaller than the abnormality threshold of the data into a normal data set, and dividing the data with the abnormality probability smaller than the abnormality threshold of the data into an abnormality data set of the operation data.
4. The new energy automobile fault pre-judging method based on the internet of things of claim 3, wherein the calculation formula of the data anomaly probability is as follows:
wherein d i (i＝1、2...n)、C 0 、D 0 Are all parameters, and C 0 ＞c i (i＝1、2...n)，D 0 ＞d i (i＝1、2...n)。
5. The new energy automobile fault pre-judging method based on the internet of things according to claim 4, wherein the data with the abnormal probability smaller than the abnormal threshold value of the data is marked while being divided into a normal data set, and the association degree W between the occurrence probability of the data and the abnormal probability of the data is calculated:
wherein Q is n The occurrence probability corresponding to the n-th normal data set.
6. The method for predicting the failure of the new energy automobile based on the Internet of things according to claim 5, wherein an alarm is not sent out when the association degree W is smaller than a preset threshold value, and an early warning is sent out when the association degree W is larger than the preset threshold value.
7. The new energy automobile fault pre-judging method based on the internet of things according to any one of claims 1-6, wherein the method is implemented by:
the information acquisition module is used for acquiring vehicle operation data of the current new energy automobile;
the real-time monitoring module is used for receiving the vehicle running data, monitoring the vehicle running state in real time, and generating vehicle suspicious data if the running state is abnormal;
the fault self-diagnosis module is used for receiving the generated vehicle suspicious data, pre-judging whether the vehicle running state has a fault according to the generated vehicle suspicious data, if the vehicle running state does not have the fault, recording the occurrence times of the generated vehicle suspicious data, if the vehicle running state does not have the fault, generating vehicle fault data, and simultaneously sending out a warning;
and the fault processing module is used for receiving the vehicle fault data and taking emergency measures according to the vehicle fault data.
8. The new energy automobile fault pre-judging method based on the internet of things of claim 7, wherein the fault self-diagnosis module comprises:
the data preprocessing module is used for preprocessing a suspicious data set of the vehicle;
the function model building module is used for building a function model, receiving the data transmitted by the data processing module and dividing a normal data set and an abnormal data set;
and the fault analysis module is used for analyzing and determining faults according to the abnormal data set.
9. The internet of things-based new energy automobile fault pre-judging method of claim 7, wherein the vehicle operation data at least comprises motor operation parameters of the new energy automobile.
10. The internet of things-based new energy automobile fault pre-judging method of claim 9, wherein the vehicle operation data further comprises sensor parameters and gearbox parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310995405.2A CN117233605A (en) | 2023-08-09 | 2023-08-09 | New energy automobile fault pre-judging method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310995405.2A CN117233605A (en) | 2023-08-09 | 2023-08-09 | New energy automobile fault pre-judging method based on Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117233605A true CN117233605A (en) | 2023-12-15 |
Family
ID=89083354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310995405.2A Pending CN117233605A (en) | 2023-08-09 | 2023-08-09 | New energy automobile fault pre-judging method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117233605A (en) |
-
2023
- 2023-08-09 CN CN202310995405.2A patent/CN117233605A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111351664B (en) | Bearing temperature prediction and alarm diagnosis method based on LSTM model | |
| CN108569607B (en) | Elevator fault early warning method based on bidirectional gating cyclic neural network | |
| CN114559819B (en) | Electric automobile battery safety early warning method based on signal processing | |
| KR20190107080A (en) | Cloud-based vehicle fault diagnosis method, apparatus and system | |
| CN212047237U (en) | Electronic detection and maintenance system based on new energy automobile control system | |
| JP6557110B2 (en) | Condition diagnosis apparatus and program | |
| CN112987687B (en) | Cloud-end integrated intelligent line control chassis health monitoring system and method | |
| CN113624291A (en) | Oil consumption monitoring method, oil consumption monitoring device and engineering vehicle | |
| EP3865963A1 (en) | Method and device for analyzing vehicle failure | |
| CN110954354A (en) | Equipment fault diagnosis method and device | |
| CN114889433A (en) | Thermal runaway alarm system and method for battery of electric vehicle | |
| CN111562496A (en) | Motor running state judgment method based on data mining | |
| CN114738132A (en) | Supercharger speed sensor fault diagnosis method and system based on real ship data | |
| CN113131019A (en) | New energy electric automobile battery module operation safety real-time supervision early warning system based on cloud calculates and thing networking | |
| CN116664015A (en) | Intelligent charging pile management system and method thereof | |
| CN113986893A (en) | Active early warning system and method based on generator car risk identification | |
| WO2020211844A1 (en) | Electric vehicle security control method based on security tree probabilities and security importance, and electric vehicle | |
| WO2022147684A1 (en) | Method and apparatus for identifying abnormalities in mechanical apparatus or mechanical component | |
| WO2020211846A1 (en) | Safety tree model-based electric vehicle operation and maintenance optimization method | |
| CN117233605A (en) | New energy automobile fault pre-judging method based on Internet of things | |
| CN117491813A (en) | Insulation abnormality detection method for power battery system of new energy automobile | |
| CN111381165A (en) | Vehicle power battery monitoring method, device and platform | |
| CN115788771A (en) | Intelligent operation and maintenance management system of wind power generation system based on Internet of things technology | |
| CN115062867A (en) | Bearing fault prediction method based on Teager energy spectrum and improved CNN model | |
| CN112525337B (en) | Pretreatment method for vibration monitoring data of mechanical press |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |